Submission Deadline: 31 December 2024 View: 644 Submit to Special Issue
Deep learning has demonstrated remarkable accomplishments in various domains, including speech recognition and image processing. While deep learning offers novel solutions for these applications, its training model necessitates a substantial volume of data. Consequently, service providers are compelled to amass extensive participant data, which may encompass confidential details pertaining to companies or users, such as medical records, account information, and business operations. The utilization of this sensitive information in deep learning applications can potentially result in the inadvertent exposure of sensitive data of enterprises or users. Simultaneously, as users become more cognizant of safeguarding their personal privacy and governments implement stricter information security laws and regulations, there is a growing emphasis in various domains on investigating multi-participant privacy-preserving deep learning.
The objective of this topical collection is to solicit novel contributions pertaining to recent advancements in privacy-preserving deep learning. This special issue endeavors to encompass a broad spectrum of subjects associated with the practical implementation of deep learning, encompassing, but not limited to:
· Privacy-preserving deep learning via homomorphic encryptions
· Privacy-preserving deep learning via differential privacy
· Privacy-preserving deep learning via secure multi-party computation
· Applications of privacy-preserving deep learning
· Privacy-preserving distributed deep learning
· Privacy-preserving federated deep learning and its applications
· Privacy-preserving deep reinforcement learning
· Deep unlearning and its applications
· Privacy-preserving deep learning via other privacy technologies
· Privacy-preserving active learning for training deep learning
· Distributed computing for privacy-preserving deep learning
· Performance optimization of privacy-preserving deep learning
· Experimental testbeds of privacy-preserving deep learning